English
Related papers

Related papers: Using Variable Threshold to Increase Capacity in a…

200 papers

We consider an additive Gaussian channel with additive Gaussian noise feedback. We derive an upper bound on the n-block capacity (defined by Cover [1]). It is shown that this upper bound can be obtained by solving a convex optimization…

Information Theory · Computer Science 2015-03-19 Chong Li , Nicola Elia

The aim of this thesis is to compare the capacity of different models of neural networks. We start by analysing the problem solving capacity of a single perceptron using a simple combinatorial argument. After some observations on the…

Disordered Systems and Neural Networks · Physics 2022-11-15 Leonardo Cruciani

While message passing neural networks (MPNNs) have convincing success in a range of applications, they exhibit limitations such as the oversquashing problem and their inability to capture long-range interactions. Augmenting MPNNs with a…

Machine Learning · Computer Science 2025-04-08 Joshua Southern , Francesco Di Giovanni , Michael Bronstein , Johannes F. Lutzeyer

Empirical studies demonstrate that the performance of neural networks improves with increasing number of parameters. In most of these studies, the number of parameters is increased by increasing the network width. This begs the question: Is…

Machine Learning · Computer Science 2021-05-04 Anna Golubeva , Behnam Neyshabur , Guy Gur-Ari

Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the performance of the models. In this paper, we explore the…

Machine Learning · Computer Science 2023-03-14 Aftab Hussain , Md Rafiqul Islam Rabin , Bowen Xu , David Lo , Mohammad Amin Alipour

The recently developed feedback trap can be used to create arbitrary virtual potentials, to explore the dynamics of small particles or large molecules in complex situations. Experimentally, feedback traps introduce several finite time…

Statistical Mechanics · Physics 2015-04-02 Yonggun Jun , John Bechhoefer

In Shannon information theory the capacity of a memoryless communication channel cannot be increased by the use of feedback from receiver to sender. In this paper the use of classical feedback is shown to provide no increase in the…

Quantum Physics · Physics 2007-05-23 Garry Bowen , Rajagopal Nagarajan

Learning-based methods could provide solutions to many of the long-standing challenges in control. However, the neural networks (NNs) commonly used in modern learning approaches present substantial challenges for analyzing the resulting…

Machine Learning · Computer Science 2022-02-03 Michael Everett

For enhancement of noisy speech, a method of threshold determination based on modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of the noisy speech by exponential distribution is presented. A custom…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-19 Md Tauhidul Islam , Celia Shahnaz , Wei-Ping Zhu , M. Omair Ahmad

In this work we study variance in the results of neural network training on a wide variety of configurations in automatic speech recognition. Although this variance itself is well known, this is, to the best of our knowledge, the first…

Machine Learning · Computer Science 2016-06-15 Ewout van den Berg , Bhuvana Ramabhadran , Michael Picheny

In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set. The memory network incorporates both internal and external memory blocks…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Chao Ma , Chunhua Shen , Anthony Dick , Qi Wu , Peng Wang , Anton van den Hengel , Ian Reid

The inclusion of a macroscopic adaptive threshold is studied for the retrieval dynamics of layered feedforward neural network models with synaptic noise. It is shown that if the threshold is chosen appropriately as a function of the…

Disordered Systems and Neural Networks · Physics 2007-05-23 D. Bolle , R. Heylen

Binary neural networks (BNNs) constrain weights and activations to +1 or -1 with limited storage and computational cost, which is hardware-friendly for portable devices. Recently, BNNs have achieved remarkable progress and been adopted into…

Machine Learning · Computer Science 2021-10-12 Jiehua Zhang , Zhuo Su , Yanghe Feng , Xin Lu , Matti Pietikäinen , Li Liu

We firstly extend the interpretation of feedback communication over stationary finite dimensional Gaussian channels as feedback control systems by showing that, the problem of finding stabilizing feedback controllers with maximal reliable…

Information Theory · Computer Science 2015-12-01 Chong Li , Nicola Elia

We consider finite state channels where the state of the channel is its previous output. We refer to these as POST (Previous Output is the STate) channels. We first focus on POST($\alpha$) channels. These channels have binary inputs and…

Information Theory · Computer Science 2013-09-24 Haim H. Permuter , Himanshu Asnani , Tsachy Weissman

Increasing the capacity of recurrent neural networks (RNN) usually involves augmenting the size of the hidden layer, with significant increase of computational cost. Recurrent neural tensor networks (RNTN) increase capacity using distinct…

Computation and Language · Computer Science 2018-05-15 Alexandre Salle , Aline Villavicencio

The capacity of time-varying channels with periodic feedback at the transmitter is evaluated. It is assumed that the channel state information is perfectly known at the receiver and is fed back to the transmitter at the regular…

Information Theory · Computer Science 2007-07-13 Mehdi Ansari Sadrabadi , Mohammad Ali Maddah-Ali , Amir K. Khandani

Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using a…

Machine Learning · Statistics 2023-05-02 Aliaksandr Hubin , Geir Storvik

Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power.…

Machine Learning · Computer Science 2025-01-13 Bingxu Zhang , Changjun Fan , Shixuan Liu , Kuihua Huang , Xiang Zhao , Jincai Huang , Zhong Liu

Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net…

Machine Learning · Computer Science 2017-06-19 Osbert Bastani , Yani Ioannou , Leonidas Lampropoulos , Dimitrios Vytiniotis , Aditya Nori , Antonio Criminisi